felo-content-to-slides

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a Node.js CLI script or a globally installed felo command to communicate with the Felo Open Platform. This is the expected mechanism for its functionality.
  • [EXTERNAL_DOWNLOADS]: Recommends installation of the felo-ai NPM package and fetches the skill from the Felo-Inc/felo-skills repository. These are verified vendor resources.
  • [CREDENTIALS_UNSAFE]: The skill utilizes FELO_API_KEY for API access. It provides secure instructions for users to configure this via environment variables or a configuration command, preventing the use of hardcoded credentials.
  • [SAFE]: Indirect Prompt Injection Surface: The skill processes external web and video content, which is a potential surface for indirect prompt injection.
  • Ingestion points: User-provided URLs and video IDs passed as arguments to the CLI in SKILL.md.
  • Boundary markers: No explicit delimiters or 'ignore' instructions are documented for the content ingestion step.
  • Capability inventory: The skill executes shell commands (via node) and performs network operations to fetch content and send it to the Felo API.
  • Sanitization: The documentation does not specify sanitization methods, but the behavior is inherent to the skill's primary purpose of content conversion.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:00 AM